TPAMI 2024 papers on Adversarial robustness and security
18 of the 666 papers published in TPAMI 2024 (2.7%) are on Adversarial robustness and security, compared with 2.7% at TPAMI 2023. They fall into 4 topics.
See TPAMI 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Certified and empirical robustness · 8 papers
- Improving Fast Adversarial Training With Prior-Guided Knowledge (66 citations)
- Mitigating Accuracy-Robustness Trade-Off via Balanced Multi-Teacher Adversarial Distillation (32 citations)
- Adversarial Attack and Defense in Deep Ranking (20 citations)
- Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks (18 citations)
- Towards Unified Robustness Against Both Backdoor and Adversarial Attacks (18 citations)
- Revisiting the Trade-Off Between Accuracy and Robustness via Weight Distribution of Filters (16 citations)
- Adversarial Training With Anti-Adversaries (4 citations)
- Provable Unrestricted Adversarial Training Without Compromise With Generalizability
Black-box and transfer attacks · 6 papers
- Diffusion Models for Imperceptible and Transferable Adversarial Attack (160 citations)
- Adaptive Perturbation for Adversarial Attack (27 citations)
- Optimizing Latent Variables in Integrating Transfer and Query Based Attack Framework (14 citations)
- STDatav2: Accessing Efficient Black-Box Stealing for Adversarial Attacks (11 citations)
- Dynamic Routing and Knowledge Re-Learning for Data-Free Black-Box Attack (7 citations)
- A Theoretical View of Linear Backpropagation and its Convergence (5 citations)
